Slashdot Mirror

The good thing is that we've had PCI to ISA bridge chips for at least a decade: https://www.altera.com/product...

So unless they are doing some seriously weird low-level signal nonsense, you would be able to get past that with some hardware hackery.

Given that FPGAs are big, slow, and hot compared to equivalent logic built as a fixed function chip(but with the obvious benefit of not being fixed function), Altera FPGAs manufactured on the fanciest processes available seem like a fairly obvious product of the acquisition..

That was going to happen anyway. Atlera announced that they were going to manufacture on Intel's newest process back in 2013.

The DE0-Nano is a barebone board and the DE2-115 is populated with various common I/O ports.

The DE0-Nano is a barebone board and the DE2-115 is populated with various common I/O ports.

Why would not Intel, with its fabs and process nodes, produce best ARM around?

Well it does already as Altera's Stratix 10 would use Intel's 14nm fabs.
http://newsroom.altera.com/pre...

But why not Intel itself?

What I would rather see in an embedded Linux board is more I/O. I am not talking about USB, HDMI or Ethernet but honest to goodness digital I/O's and serial busses like I2C or SPI. The minnowboard has a measly 8 GPIO's and two more hardwired to LED's. That isn't worth $200 when I can get the same thing by purchasing a cheap Atom ITX board and then adding an FPGA PCI I/O card from Mesa Electronics for slightly more.

If you want to impress me and make it worth $200 then how about using the Intel Atom Processor E6x5C featuring an embedded Altera FPGA which is connected to the CPU by a friggen PCIe Gen2 x1 link. Then include a default bitfile for the FPGA which gives you a bunch of GPIO, PWM and UARTS for serial ports like RS232, SPI and I2C. Also breakout the remaining PCIe link for further expansion. A kernel driver will then expose the various I/O devices inside the FPGA to a standard API. Then port the Wiring libs which is used by the Arduino to the new API for the FPGA and you will now have a development board that will blow the competition away. Even the Arduino IDE can be modified to build Linux binaries for the new API. Bonus points of you throw a nice 8 channel 16 bit high speed ADC on there. No re-learning new libraries or languages. Arduino libs could be added without code modification provided they don't make low level calls. Even then simple modifications could be made to port them. The API could also be called from any other language like C++, Go, Ada, D or whatever you fancy so you can write code in your language of choice. Newbies could plug in the board wait for it to boot and configure the FPGA and start writing code and wiring it into their projects, they already know Arduino libs so let them use those. If you really want to be fancy use the RT PREEMPT patch and let more advanced users write code for real time stuff guaranteeing determinism.

Imagine then if the internal FPGA bits could then be added to or modified to include new I/O devices. Establish a standard bus and I/O address space for the FPGA and make a template for writing new modules. Write a GUI editor which lets you snap modules onto the bus like Legos and set the address space and their I/O pins. Call Quartus using scripts in the background and generate the new bitfile which can be uploaded on the fly to the FPGA from the host OS. Then the standard API for the kernel driver would simplify writing libraries for talking to the new modules. Want to make a CNC? Add quadrature encoder interfaces and H bridge controllers and directly drive servo motors. Software radio, DSP, video processing, audio processing, the possibilities are endless. Then the community can release HDL modules which the user can snap into their designs and then do the wiring. This way people don't have to learn complex HDL programming, they use what the community provides. Don't like the default bitfile layout or standard templates? Write your own HDL code and do what you please. Open hardware means you have all the specs and source.

If that were available for 200-300 then I would gleefully say shut up and take my money.

Ah, I see.

Yes, in that case, they just don't like debian. Just like Oracle don't, which is why if you want to run most Oracle server products you really need RHEL or at the very least centos. Same with many other commercial vendors who support Linux (random example, which just happens to be the latest commercial software I acquired).

consider an inexpensive FPGA board like the Altera DE1. There are nearly unlimited things you can build based off such a kit, whether you decide to look at it from the viewpoint of hardware, software or both. http://www.altera.com/education/univ/materials/boards/de1/unv-de1-board.html
(there are several other low cost FPGA boards, I just happen to use the DE1. It's quite adequate for a great many things, but there may be even better options out there by now)

Also, consider amateur radio. If you have an active local club, it will server as a gateway into a whole realm of interesting things (many only tangentially related to radio) and an introduction to the people who are doing them locally.

The move to GPU's won't happen in HPC circles. However the move of OpenCL to FPGAs is happening:

http://www.altera.com/corporate/news_room/releases/2011/products/nr-opencl.html

why doesn't the sat phone provider build in a crappy little GSM/CDMA into the hand unit, and then gateway from the cell phone network into the sat phone

The SWaP of such a hybrid unit will be determined by the satellite portion. Who would want to always carry a large phone if they know that they aren't going to suddenly end up in a desert instead of their cubicle at work? [A: only these.]

I sometimes find myself in the middle of nowhere, without cell coverage - usually at a safe distance from the civilization. I don't have a sat phone, but if I did I'd want it to be a separate unit. I'd keep it in the car, and if once in a blue moon I must make a call from a no-coverage spot I'd take it and power it up.

An XFI-SFI interconnect runs up to 10.3 Gbps on a single serial link. It is double-pumped (bit on each end of the clock) so the clock rate is half that. This is the connection that links a 10Gbps phy to the transceiver module. You do have to keep the interconnects pretty short though.

http://www.altera.com/technology/high_speed/protocols/10gb-ethernet-xfi-sfi/pro-xfi-sfi.html

XDR ram can transmit 8 bits per clock on a serial line: http://en.wikipedia.org/wiki/XDR_DRAM

how the Russian lag in developing VLSI chips curiously did not critically hinder their accomplishments in space missions, ICBMs and chess computation.

VLSI is not necessarily an advantage in space missions. You can do a lot of embedded computing just using low density, but radiation hardened parts. USSR had several chipsets that were suitable for military and space use. I can't find them on the Web right now (forgot their p/n). With regard to SWaP, one engineer told me "our rockets are powerful enough" :-)

I'm using Altera tools for work right now. We have a paid seat, but even in free mode, the web kit is powerful enough to do pretty complex stuff. To experiment with the software, go to altera.com, click download in the upper right corner and download the web kit. Unfortunately, the linux version is not free but you can use it for 30 days without a license. Xilinx also has a free version you can use. As for development boards, here's the cheapest FPGA board I found for Altera: http://www.altera.com/products/devkits/altera/kit-cyc2-2C20N.html I'm using the Cyclone III version of that board. Its quite good. For a Cyclone I board, these look inexpensive and have a wide range of features: http://www.knjn.com/ShopBoards_USB2.html Xilinx has a lot of development boards as well. My experience with Xilinx is better in the support department than Altera. They will give you the software and even dev hardware if you ask nicely. But their software takes more than 12 hours (yes twelve hours) to install and update on a core 2 duo machine. Sad really. The altera software is lighter feeling but just as powerful and seems to be more ... what's the word: friendly. I haven't used Xilinx in a while but I had a hellofa time with it, when I was trying to prototype asics with Virtex II. Altera is currently under mandate to make money from their software, even though they are a hardware company. That makes getting a free license almost impossible. Too bad for them. I've been getting great support for Altera from Octera Solutions (as opposed to Altera itself). Perhaps they can help you. If you're brand new to hardware, you might want to learn Verilog or VHDL first. I think both Xilinx and Altera's web kits come with Modelsim. Its a stripped down version but it will be fine to learn the basics.

I write FPGA code for a living, more in VHDL than Verilog, and more for Xilinx than Altera.

I would actually recommend that you don't buy a board at first. You can pick one out so you can decide on a vendor's chip, that's fine, but simulate everything, because that's what HDL design is all about. Both vendors offer a free version of their toolset and there's a free simulator with each of those. Or you can download ModelSim Starter edition. I wouldn't call either one Linux friendly.

As far as the board goes, I would recommend one of Altera's Nios II Embedded Dev Kits. I feel that although Altera has a slightly steeper learning curve than Xilinx, they also have a nicer overall package than what Xilinx is currently offering. I'm speaking from the point of embedding a soft processor though, if that doesn't interest you, then either of the cheap Altera Cyclone or Xilinx Spartan kits will get the job done.

This is the only book you need on VHDL: The Designer's Guide to VHDL by Peter Ashenden.

I haven't found a Verilog book of similar quality.

Buy several books on Verification and testbench writing. That's where the real work comes in, and it's significantly more work than whatever circuit design you're doing. Spend the time to learn how to write self-checking testbenches.

Read over the Synthesis guides for whatever vendor's board you choose. Understand how the constructs you use affect synthesis. There's a wealth of information in the Xilinx and Altera online documentation. There's also a lot of really of good snippets of code which are themselves useful but also typically contrast less and more effective constructs for synthesis.

And finally, I will echo the caution that HDL is not a programming language, it is a design language. If you do not have a fundamental grasp of circuits, logic design, and computer architecture, I would recommend you pursue those topics first.

Xilinx: http://www.xilinx.com/products/devkits/HW-SPAR3AN-SK-UNI-G.htm

Altera: http://www.altera.com/products/devkits/altera/kit-cyc3-starter.html

Both are very mainline FPGAs, both have full devkits, references designs, include the tools, linux support on Xilinx at least (not sure on Altera), and are both at your price point.

This entire thread has been about the effectiveness of the current U.S. policy regarding export restrictions. snowgirl argued, in part, that the restrictions are socially ineffective, I've argued that they are logistically ineffective. I've even argued for new or different policies and laws: "Resources applied to enforcing policies which have been demonstrated to be incompletely effective (or, ineffective), can instead be applied to try newer, more effective policies."

No, Snow girl argues that she didn't see the need for the restrictions. I set her strait on that. You came in saying something about Iran's neighbors getting access to the stuff with E-waste as if that mattered. I pointed out that it didn't matter then you picked up on the effectiveness of embargoes. Either way, you don't give people who claim to want to hurt you or your friends the raw materials to make that easy. I don't know how much simpler that statement can be made.

Your position here is unclear, but the underlined sentence highlights where we differ fundamentally. It is my contention that the citizens of an effective democratic government should be able to cause laws to be changed, and that the application and enforcement of laws should not be completely uniform and without judgment. Contemporary practice indicates that the U.S. export control regime agrees with at least the second part of my contention, insofar as they inspect only one percent of eligible goods entering and exiting the U.S., they do next to nothing to practically restrict the export of digital munitions (encryption products) via software, and they do not prevent restricted military surplus from being auctioned and exported abroad from on-line stores legally incorporated in the U.S.

My point is pretty clear, I'm not sure how your missing it. If you want the law changed, then work to change it. If no one agrees with you, then don't violate the law or don't expect sympathy when you get busted. And your wrong, they do quite a bit to track and control exports. Of course they rely a lot on self reporting and people following the laws but they also track imports into restricted companies. Not catching one actor for a period of time isn't proof that they don't do enough, it it proof that one actor violated the law and needs to be held accountable for it. In this case, it appears to be a flagrant violation of the law which will probably involve jail time for someone at HP as well as massive fines.

Unless someone specifically complains that some U.S.-based legal entity at HP or any other company is exporting to Iran, I would expect the enforcement agencies to focus on more effective sections of the existing legislation. It is much more useful to prevent new engineering designs and components which would enhance the range and lethality of weapons from reaching Iran, than to stop the flow of consumer electronics which provide next to no enhancement to their existing weapons and capabilities, WHETHER OR NOT such devices are easily obtainable.

So you don't think the 500mhz mips processor in most HP office machines or even the smaller 200 MHZ processors in the P1006 or the 4200N laser desktop printers wouldn't do that with the munitions capabilities? It is more powerful then most Stratix based missile guidance systems in early ICBM systems. Chain a series of these together with just half the memory that comes stock in a a 9500hdn, ad a GPS and outside of hardening, you have the effective equivalent of 1990's era cruise missile and smart bomb guidance systems. This is without even considering the EIO device specs like the 620n jet direct cars that come with them. Of course it would require the disassembl

Based on my half remembered conversations from 10 years ago, FPGAs are great for prototyping, but not for flight systems, because they are power hogs.

When you measure your power consumption in surface area of solar panel and weight of battery that need to be put on orbit...

With your typical Xilinx FPGA, power consumption would be the least of your problems. Even with unlimited power, single event upset problems would prevent them from being usable in anything you put into orbit. There have been a number of white papers written on this problem, such as from Xilinx and Altera as well as Actel (sort of) [PDF warning].

For the people talking about use only in low-volume items: I recently looked at the innards of a couple of thoroughly mass-market oriented LCD TVs that each included an FPGA. A small FPGA isn't necessarily all that expensive, and can allow things like doing a single physical design that works with either PAL or NTSC, depending purely on how you program one part...

Why not go for a slightly higher end FPGA board.. Altera do some great development kits: http://www.altera.com/products/devkits/kit-dev_pla tforms.jsp and you can then get some bread board and drive anything you want though various I/O ports on the boards.

Why not make a CPU with a built-in FPGA, then load bits of the kernel into that hardware?

Were you thinking of something a lot different from the Xilinx Virtex 4 FX, Altera Excalibur or Atmel part (referred to elsethread)?

> There should be some standard interchange format for the FPGA data. gcc should be able to take some C code an output FPGA intermediate programming data from it.

Smile! This stuff already exists for years:

You just have to build a library that

• shoves "compiled" logic chunks to the chip
• uses the FPGA-board's upload functionality as a pluggable driver
• does the resource management.

Everything else is already there.

• You can get some FPGA developer board to develop and test your library:
• You can use SPARK to compile your C-code to VHDL.
• I guess VHDL can be uploaded directly to the FPGA. If not maybe stuff like gEDA or similar stuff for VHDL helps...
• I am a total n00b in things of hardware design, but i found this in 1-2 hous of investigation and reading via wikipeda.

The problem is that FPGA-boards are pretty expensive... (The least expensive i found was some 66MHz devboard for 150$. The most expensive had 500MHz and a price tag of ~7000$!! [including a ton of golden analog contacts and stuff ;])

> There should be some standard interchange format for the FPGA data. gcc should be able to take some C code an output FPGA intermediate programming data from it.

Smile! This stuff already exists for years:

You just have to build a library that

• shoves "compiled" logic chunks to the chip
• uses the FPGA-board's upload functionality as a pluggable driver
• does the resource management.

Everything else is already there.

• You can get some FPGA developer board to develop and test your library:
• You can use SPARK to compile your C-code to VHDL.
• I guess VHDL can be uploaded directly to the FPGA. If not maybe stuff like gEDA or similar stuff for VHDL helps...
• I am a total n00b in things of hardware design, but i found this in 1-2 hous of investigation and reading via wikipeda.

The problem is that FPGA-boards are pretty expensive... (The least expensive i found was some 66MHz devboard for 150$. The most expensive had 500MHz and a price tag of ~7000$!! [including a ton of golden analog contacts and stuff ;])

> There should be some standard interchange format for the FPGA data. gcc should be able to take some C code an output FPGA intermediate programming data from it.

Smile! This stuff already exists for years:

You just have to build a library that

• shoves "compiled" logic chunks to the chip
• uses the FPGA-board's upload functionality as a pluggable driver
• does the resource management.

Everything else is already there.

• You can get some FPGA developer board to develop and test your library:
• You can use SPARK to compile your C-code to VHDL.
• I guess VHDL can be uploaded directly to the FPGA. If not maybe stuff like gEDA or similar stuff for VHDL helps...
• I am a total n00b in things of hardware design, but i found this in 1-2 hous of investigation and reading via wikipeda.

The problem is that FPGA-boards are pretty expensive... (The least expensive i found was some 66MHz devboard for 150$. The most expensive had 500MHz and a price tag of ~7000$!! [including a ton of golden analog contacts and stuff ;])

You can buy this of the shelf: http://www.altera.com/products/devkits/altera/kit- pci-2c35.html

I wonder, though... if ClearLogic had worked only from data-sheets, and not examined the chips at all, would this decision still have applied to them? Were they copying things like the distance between different functional units, or just the pinout and the logical structure of the chip?

It looks like even the ClearLogic domain name (formerly www.clear-logic.com) is gone. Too bad...

I wonder, though... if ClearLogic had worked only from data-sheets, and not examined the chips at all, would this decision still have applied to them? Were they copying things like the distance between different functional units, or just the pinout and the logical structure of the chip?

It looks like even the ClearLogic domain name (formerly www.clear-logic.com) is gone. Too bad...

This is pretty darn close to what was happening. There's a little more to the story: Clear Logic not only hijacked Altera's masks, bitstream and programmer, they were also providing Altera's CAD software, Quartus II, as the CAD development environment for their users. Their flow for their users was: design and debug in Quartus II, send the bitstream to Clear Logic, get an ASIC back, bypass Altera.

Correct link is http://altera.com/

• comp.arch.fpga Google archive of Usenet groups, where people interested in FPGA hang out.
• Opencores A set of free IP cores that can be implemented in FPGAs
• Comprehensive tutorial on FPGA
• A comprehensive list of FPGA CPUs
• A good FPGA tools overview
• FPGAworld news, jobs, forums, demos etc.(http://www.fpgaworld.com)
• FPGA Basics by Ray Andraka
• Fpga4Fun various fpga projects
• FPGA Boards
• AP100 PCI Platform FPGA Development Board
• Information about signal processing on FPGA by RF Engines
• FPGA manufacturers
  • Xilinx Xilinx has traditionally been the FPGA leader. Their general philosophy is to provide all the features possible, at the cost of extra complexity.
  • Altera Altera is the second FPGA heavyweight. Their philosophy is to provide the features that most people want while keeping their devices easy to use.
  • Lattice Lattice's focus is on low-cost, feature-optimized FPGAs and non-volatile, flash-based FPGAs.
  • Actel (http://www.actel.com/) and QuickLogic have antifuse (programmable-only-once) products.
  • Cypress
  • Atmel
  • Debian FPGA.

Someday we will have devices that - IF they need to be plugged in - will communicate with the power supply its needs in terms of power handling, voltage, and ripple requirements (or desires). While adapters could provide a means for some time to power the devices that will not communicate (use a switch to manually select), eventually things should be plugNplay - just like your USB mouse. (It's too bad USB can't handle more power at this point....)

This power supply could provide a few hundred watts, run off any voltage (AC or DC) to step (buck or boost) and switch (provided the current on the supply side is available) to the proper output voltage. 3-6 wires and some sort of universal plug would be sufficient to provide a serial comms link and power/ground for a few different supplies to a number of devices.

I can imagine having to buy a large one for your computer desk, and maybe a smaller one for your phone/answering machine/etc. (If they're still around).

The connectors should be bisexual so you can connect a number of cords together without worrying about which end is which (or having to buy matched pairs and end up with extras for DIYers) to get to your device. Feedback from the device on power quality or voltage drop would be nice (expensive however) to compensate at the supply for bad contacts or extra long runs.

NatSemi will eventually come out with an integrated controller that takes care of the signaling (including PHY), all control functions, and the kitchen sink - all somebody has to do is provide the transformer, diodes, filter caps, and case. This will make these easy to manufacture and then companies can compete on form factor, efficiency and cost rather than trying to get you to buy their proprietary cables and yet another wall wart for your [whatever].

A controller that could plug into a spare ATX power supply that would properly load it and provide a number of different voltages and a cabling system with converters to a number of different barrel connector sizes and polarities would be nice :) to start however. Happy 420!

You can actually already run uCLinux on a NIOS II soft processor implemented in even the smallest Altera Cyclone II FPGA but you do need external memory.
I don't think even the largest FPGA in the world with its 9 megabits of internal memory has quite enough internal memory to run Linux yet.

You can actually already run uCLinux on a NIOS II soft processor implemented in even the smallest Altera Cyclone II FPGA but you do need external memory.
I don't think even the largest FPGA in the world with its 9 megabits of internal memory has quite enough internal memory to run Linux yet.

You can actually already run uCLinux on a NIOS II soft processor implemented in even the smallest Altera Cyclone II FPGA but you do need external memory.
I don't think even the largest FPGA in the world with its 9 megabits of internal memory has quite enough internal memory to run Linux yet.

It's about time we get extensible languages as we have had extensible processors for a couple of years already e.g. Altera's NIOS : http://www.altera.com/niosii

An interesting (and excellent) link on VHDL coding standards in a working environment is also available off that page: the European Space Agency's VHDL coding standard (available in PostScript format here http://tech-www.informatik.uni-hamburg.de/vhdl/doc /style_guide/ModelGuide.ps.gz).

The Xilinx WebPack is a great place to start - you get everything you need to take you from text-edited files to a binary image on one CD (or download from here: http://support.xilinx.com/support/download.htm). It even comes with a (very) cut-down version of Mentor Graphics' ModelSim and Xilinx's own synthesis tool, XST.

If you use Altera chips, they have a similar offering, called Quartus II Web Edition (http://www.altera.com/products/software/products/ quartus2web/sof-quarwebmain.html)

Speaking of text editors, (X)Emacs has a great VHDL mode that can beautify your code, create makefiles and manage your projects, available here:http://opensource.ethz.ch/emacs/vhdl-mode.htm l.

Check out:

Fundamentals of Digital Logic by Brown & Vranesic

Available in both a VHLD and Verilog version for your learning pleasure. Both books ship with a copy of Quartus II from Altera. You can get Altera development kits here if you're looking for something bigger and better than a Spartan-IIe.

Disclaimer: I work with the authors.

Check out:

Fundamentals of Digital Logic by Brown & Vranesic

Available in both a VHLD and Verilog version for your learning pleasure. Both books ship with a copy of Quartus II from Altera. You can get Altera development kits here if you're looking for something bigger and better than a Spartan-IIe.

Disclaimer: I work with the authors.

We use the Altera MAX 7000S in our digital systems classes. The software it uses, Quartus II. is very easy to use and can do pretty much anything you'd ever need. All you have to do is wire up the board once, then download your projects there. 16 dip switches, 4 push buttons, 2 seven segment displays, 16 leds, and pin outs for everything. Plus PS/2, VGA ports, and a bunch of voltage/temp/IO sensors. Nifty little device...

Another good choice might be Altera Quartus II (used to be Maxplus II). It's a pretty comprehensive software package and it's free.

Though not the same as this, the Xilinx Vertex II Pro combines an FPGA and PowerPC risc core on the same chip.

The Altera Excalibur does something similar with an ARM processor core and programmable logic.

Both of these have been around for a while...

If you think putting together a processor and an FPGA is revolutionary I think you need to look at Xilinx (Virtex II Pro) and Altera. Both of them have CPU + FPGA combinations. Xilinx is a PowerPC 405 core, Altera is an ARM9 (I think).

Xilinx also has an FPGA that has enough space to implement a full PowerPC 405 processor.

This to me indicates more of a simple evolution then revolution...

You can get the Tarball from OpenCores, and the compiler and hardware from xilinix, altera, Lattice Semiconductor, etc.

I'd like to see some tests run on the performance of the new system.

You might loose in data-transfer rate. Depends on the hardware. Anything from full bus speed to significantly slower can be built and bought. Look e.g. here for a really fast AES chip.

What will not noticably suffer however even with a slow solution is access speed. So depending on you disk usage pattern a flower solution might still be acceptable.

Don't get out much, do you?

This is relatively simple to do, and most of the major FPGA vendors offer "PCI development kits" which allow you to develop your own PCI card using their FPGAs. They're quite expensive, though, as they're aimed at OEMs.

The biggest problem in this, is that the compilers are propetary and expensive.

That would be why FPGA Vendors like Altera, Xilinx and Lattice all offer free versions of their FPGA software that will place-and-route most of their lower-cost devices.

Learning to "program" an FPGA isn't all that hard, it's just a different paradigm to program a sequential language. Interfacing the PCI bus is probably the hardest part, but most of the vendors will help you with that, too. They're in the market to sell as many FPGA chips as they can, after all...

here

Altera has a student program where you can get the UP1 board with a Altera Max and Altera Flex FPGA. The board and the book "Rapid Prototyping of Digital Design" by James O. Hamblin and Michael D. Furman. Info can be found at http://www.altera.com/education/univ/kits/unv-kits .html.
The kit costs about $150(US).

This is an Altera board containing an FPGA with embedded ARM922T cpu.

You can program the FPGA by simply doing cat system.sbi >/dev/pld0.

god I hate PPC infact I nearly hate it as much as x86 but...

now ARM a nice little design there is the same deal but with a ARM that altera do and see www
and MIPS have been doing a dev board with a hard and soft core mix for a while

well you never guess they ALL come with GNU tools and as they use standard arch that linux is already ported to

really what you want to get into is a CPU on a FPGA and one that you dont have to pay a licence for this is what opencores.org is about and credit to them flextronics have started looking at it for a solution see

news about the use of open hardware at

the openRisc 100 project at

See the FAQ at

hope that helps

regards

John Jones

There is a chip available. Check out Cyclone

It costs in the region of $15 to $40 in quantity depending on type and is completely reprogrammable. I've just been to see a demo of this chip (+ others) and it looks ideal for codec implementations. You can program it to be a processor if you want with complete control over the instruction set. These means you can build in such things as hardware complex multiplications, vector processors etc. if you want.

Watch out for this chip, it (and its big brother Stratix) will be many products in the future (certainly the ones I will be developing anyway :-)

There is a chip available. Check out Cyclone

It costs in the region of $15 to $40 in quantity depending on type and is completely reprogrammable. I've just been to see a demo of this chip (+ others) and it looks ideal for codec implementations. You can program it to be a processor if you want with complete control over the instruction set. These means you can build in such things as hardware complex multiplications, vector processors etc. if you want.

Watch out for this chip, it (and its big brother Stratix) will be many products in the future (certainly the ones I will be developing anyway :-)

We can program the FPGA with Intel instruction set compatibility, where Palladium instructions would be ignored, or design an add-on chip (like the old Pentium Turbo snap-on chips) which would detect the Palladium opcodes on the FSB and skirt around them. Whoa, am I violating the DMCA by suggesting this?

Government + Corporations versus Consumers, Saddam is just a distraction